Downloads · 30 days
6
4% of all-time downloads
USS-reward-model-utterance-with-history
athirorg/USS-reward-model-utterance-with-history
USS-reward-model-utterance-with-history is a machine learning model from athirorg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
136
Public
Parameters
396M
15.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.2 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- modernbert
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026
- SHA
- fada503b
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
USS-reward-model-utterance-with-history
This model is a fine-tuned version of answerdotai/ModernBERT-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1063
- Mse: 0.1063
- Mae: 0.1511
- R2: 0.0278
- Spearman Correlation: -0.0018
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Spearman Correlation |
|---|---|---|---|---|---|---|---|
| 2.2944 | 1.0 | 591 | 0.1483 | 0.1483 | 0.2698 | -0.3561 | nan |
| 1.1189 | 2.0 | 1182 | 0.1079 | 0.1079 | 0.1692 | 0.0130 | nan |
| 1.0480 | 3.0 | 1773 | 0.1327 | 0.1327 | 0.2664 | -0.2131 | nan |
| 1.0150 | 4.0 | 2364 | 0.1076 | 0.1076 | 0.1544 | 0.0162 | nan |
| 0.9418 | 5.0 | 2955 | 0.1063 | 0.1063 | 0.1511 | 0.0278 | -0.0018 |
| 0.8678 | 6.0 | 3546 | 0.1120 | 0.1120 | 0.2055 | -0.0243 | -0.0018 |
| 0.7709 | 7.0 | 4137 | 0.1102 | 0.1102 | 0.1855 | -0.0080 | -0.0037 |
| 0.6529 | 8.0 | 4728 | 0.1091 | 0.1091 | 0.1804 | 0.0022 | 0.0301 |
| 0.4854 | 9.0 | 5319 | 0.1129 | 0.1129 | 0.1887 | -0.0325 | 0.0155 |
| 0.3118 | 10.0 | 5910 | 0.1187 | 0.1187 | 0.2019 | -0.0854 | 0.0578 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.12.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2
- Library
- transformers
- Type
- modernbert
- License
- apache-2.0
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026